arXiv subjects

Mark Santolucito

Publications and source records attributed to Mark Santolucito.

At least 19 recordsLinked to original sources

arXiv2026

Learning GR(1) Specifications from Traces

Constrained specification mining enables the automatic discovery of desired properties from system traces. Generalized Reactivity of Rank 1, or GR(1), is a fragment of LTL with polynomial-time synthesis that natively encodes assume-guarantee properties present in most hardware and robotics domains. In this paper, we present GR1MINE, a SAT-based tool for efficiently learning GR(1) formulas from examples. We exploit the GR(1) temporal skeleton to incrementally enumerate formula candidates, leveraging learnt clauses to avoid recomputation. On the Boolean GR(1) Syntech suite, GR1MINE learns a realizable formula for all 60 benchmarks over 30X faster than generic and constrained LTL mining tools. On non-GR(1) specifications from SYNTCOMP, GR1MINE is still able to recover >2X more realizable specifications than baselines within the timeout.

cs.LO↗

arXiv2026

Experiential Learning of Runtime Monitoring Using Pachinko

We present documentation of a classroom assignment that teaches runtime monitoring through a creative embedded systems build: an interactive Pachinko game. The assignment centers on a dual-core ESP32 workflow in which students write RTLola specifications for monitors, compile these monitors to C, and deploy them alongside sensor and actuator control logic. Pachinko game events are logged in real time and used to trigger sound, animation, and motor behavior according to formal temporal logic specifications. This work showcases how formal methods can be taught in a hands-on, project-based setting for learners in a creative and classroom-scale setting. We also discuss portability: the assignment template, hardware stack, code base, and assessment approach are designed and documented to be replicated in other embedded systems, creative computing, or makerspace-style courses. This assignment was given to the students of Creative Embedded Systems (COMS3930) at Barnard College.

cs.CY↗

arXiv2026

Lattice Deduction Transformers

We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent state through a lattice between forward passes. We train on-policy in a process that mirrors deduction in a search-based constraint solver and supervise training via a domain-agnostic, abstract-interpretation-based approximation of the set of solution candidates. An $800$K-parameter LDT achieves $100\%$ accuracy on Sudoku-Extreme and Snowflake Sudoku, at a fraction of the training cost of prior small recurrent reasoners, while remaining empirically sound: the model returns a correct answer or abstains. A $1.8$M-parameter variant reaches $99.9\%$ accuracy on Maze-Hard. Frontier LLMs score $0\%$ on all three benchmarks.

cs.LG↗

arXiv2026

BlindMarket: Enabling Verifiable, Confidential, and Traceable IP Core Distribution in Zero-Trust Settings

We present BlindMarket, an end-to-end zero-trust distribution framework for hardware IP cores. BlindMarket allows two parties, the IP user and the IP vendor, to complete an IP trading process with strong guarantees of verifiability and confidentiality before the transaction, and then traceability after. We propose verification heuristics and adapt the cone of influence-based design pruning to overcome the limited scalability common to cryptographic protocols and the hardness of the underlying hardware verification. We systematically evaluate our framework on a diverse set of real-world hardware benchmarks, and the results demonstrate that BlindMarket effectively completes across a diverse set of real-world hardware IP cores, demonstrating successful verification on 12 out of 13 designs and substantial performance improvements enabled by design pruning and control-flow guided heuristics.

cs.CR↗

arXiv2026

Warm Starting State-Space Models with Automata Learning

We prove that Moore machines can be exactly realized as state-space models (SSMs), establishing a formal correspondence between symbolic automata and these continuous machine learning architectures. These Moore-SSMs preserve both the complete symbolic structure and input-output behavior of the original Moore machine, but operate in Euclidean space. With this correspondence, we compare the training of SSMs with both passive and active automata learning. In recovering automata from the SYNTCOMP benchmark, we show that SSMs require orders of magnitude more data than symbolic methods and fail to learn state structure. This suggests that symbolic structure provides a strong inductive bias for learning these systems. We leverage this insight to combine the strengths of both automata learning and SSMs in order to learn complex systems efficiently. We learn an adaptive arbitration policy on a suite of arbiters from SYNTCOMP and show that initializing SSMs with symbolically-learned approximations learn both faster and better. We see 2-5 times faster convergence compared to randomly initialized models and better overall model accuracies on test data. Our work lifts automata learning out of purely discrete spaces, enabling principled exploitation of symbolic structure in continuous domains for efficiently learning in complex settings.

cs.LG↗

arXiv2026

Mining Beyond the Bools: Learning Data Transformations and Temporal Specifications

Mining specifications from execution traces presents an automated way of capturing characteristic system behaviors. However, existing approaches are largely restricted to Boolean abstractions of events, limiting their ability to express data-aware properties. In this paper, we extend mining procedures to operate over richer datatypes. We first establish candidate functions in our domain that cover the set of traces by leveraging Syntax Guided Synthesis (SyGuS) techniques. To capture these function applications temporally, we formalize the semantics of TSL$_f$, a finite-prefix interpretation of Temporal Stream Logic (TSL) that extends LTL$_f$ with support for first-order predicates and functional updates. This allows us to unify a corresponding procedure for learning the data transformations and temporal specifications of a system. We demonstrate our approach synthesizing reactive programs from mined specifications on the OpenAI-Gymnasium ToyText environments, finding that our method is more robust and orders of magnitude more sample-efficient than passive learning baselines on generalized problem instances.

cs.LO↗

arXiv2025

TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation

Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning. We introduce TempoBench, the first formally verifiable temporal benchmark that isolates counterfactual causal attribution over execution trajectories, and we show that LLMs categorically fall back to brute-force simulation-based reasoning to solve causal reasoning problems. Built from synthesized deterministic Mealy machines, TempoBench provides an infinitely scalable corpus of trajectory-based causal reasoning problems with controllable complexity and provably correct causal labels. Frontier models reach 96% step accuracy simulating a system forward, and fall to 32% when asked which inputs were necessary for an observed output, displaying what we call the SIM/MIN gap. Our findings show that LLMs cannot reliably identify minimal necessary causes, often confusing ``possible inputs'' with ``necessary causes,'' demonstrating an inability to understand which inputs were not needed. This failure is critical for deployment in causal inference tasks such as debugging, root cause analysis, and task planning where agents must use counterfactual reasoning to plan for specific desired outcomes. We show that training on TempoBench yields a targeted gain on causal benchmarks in open-source models while matching general-purpose, math, and code reasoning datasets on standard benchmarks. This indicates counterfactual causal reasoning is a learnable, architecturally distinct capability that sits on top of existing reasoning competencies.

cs.AI↗

arXiv2025

Embedding Alignment in Code Generation for Audio

LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LLM, users may benefit from considering multiple varied code candidates to better realize their musical intentions. Code generation models, however, struggle to present unique and diverse code candidates, with no direct insight into the code's audio output. To better establish a relationship between code candidates and produced audio, we investigate the topology of the mapping between code and audio embedding spaces. We find that code and audio embeddings do not exhibit a simple linear relationship, but supplement this with a constructed predictive model that shows an embedding alignment map could be learned. Supplementing the aim for musically diverse output, we present a model that given code predicts output audio embedding, constructing a code-audio embedding alignment map.

cs.MM↗

arXiv2025

Research Vision: Multi-Agent Path Planning for Cops And Robbers Via Reactive Synthesis

We propose the problem of multi-agent path planning for a generalization of the classic Cops and Robbers game via reactive synthesis. Specifically, through the application of LTLt and Coordination Synthesis, we aim to check whether various Cops and Robbers games are realizable (a strategy exists for the cops which guarantees they catch the robbers). Additionally, we construct this strategy as an executable program for the multiple system players in our games. In this paper we formalize the problem space, and propose potential directions for solutions. We also show how our formalization of this generalized cops and robbers game can be mapped to a broad range of other problems in the reactive program synthesis space.

cs.LO↗

arXiv2024

Using a Feedback Loop for LLM-based Infrastructure as Code Generation

Code generation with Large Language Models (LLMs) has helped to increase software developer productivity in coding tasks, but has yet to have significant impact on the tasks of software developers that surround this code. In particular, the challenge of infrastructure management remains an open question. We investigate the ability of an LLM agent to construct infrastructure using the Infrastructure as Code (IaC) paradigm. We particularly investigate the use of a feedback loop that returns errors and warnings on the generated IaC to allow the LLM agent to improve the code. We find that, for each iteration of the loop, its effectiveness decreases exponentially until it plateaus at a certain point and becomes ineffective.

cs.SE↗

arXiv2024

Combining LLM Code Generation with Formal Specifications and Reactive Program Synthesis

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight and verification. In particular, they perform poorly at generating code for highly complex systems, especially with unusual or out-of-sample logic. For such systems, verifying the code generated by the LLM may take longer than writing it by hand. We introduce a solution that divides the code generation into two parts; one to be handled by an LLM and one to be handled by formal methods-based program synthesis. We develop a benchmark to test our solution and show that our method allows the pipeline to solve problems previously intractable for LLM code generation.

cs.SE↗

arXiv2024

Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages

Node-based programming languages are increasingly popular in media arts coding domains. These languages are designed to be accessible to users with limited coding experience, allowing them to achieve creative output without an extensive programming background. Using LLM-based code generation to further lower the barrier to creative output is an exciting opportunity. However, the best strategy for code generation for visual node-based programming languages is still an open question. In particular, such languages have multiple levels of representation in text, each of which may be used for code generation. In this work, we explore the performance of LLM code generation in audio programming tasks in visual programming languages at multiple levels of representation. We explore code generation through metaprogramming code representations for these languages (i.e., coding the language using a different high-level text-based programming language), as well as through direct node generation with JSON. We evaluate code generated in this way for two visual languages for audio programming on a benchmark set of coding problems. We measure both correctness and complexity of the generated code. We find that metaprogramming results in more semantically correct generated code, given that the code is well-formed (i.e., is syntactically correct and runs). We also find that prompting for richer metaprogramming using randomness and loops led to more complex code.

cs.SE↗

arXiv2024

Procedural Adherence and Interpretability Through Neuro-Symbolic Generative Agents

The surge in popularity of large language models (LLMs) has opened doors for new approaches to the creation of interactive agents. However, managing and interpreting the temporal behavior of such agents over the course of a potentially infinite interaction remain challenging. The stateful, long-term horizon reasoning required for coherent agent behavior does not fit well into the LLM paradigm. We propose a combination of formal logic-based program synthesis and LLM content generation to bring guarantees of procedural adherence and interpretability to generative agent behavior. To illustrate the benefit of procedural adherence and interpretability, we use Temporal Stream Logic (TSL) to generate an automaton that enforces an interpretable, high-level temporal structure on an agent. With the automaton tracking the context of the interaction and making decisions to guide the conversation accordingly, we can drive content generation in a way that allows the LLM to focus on a shorter context window. We evaluated our approach on different tasks involved in creating an interactive agent specialized for generating choose-your-own-adventure games. We found that over all of the tasks, an automaton-enhanced agent with procedural guarantees achieves at least 96% adherence to its temporal constraints, whereas a purely LLM-based agent demonstrates as low as 14.67% adherence.

cs.AI↗

arXiv2024

Guiding LLM Temporal Logic Generation with Explicit Separation of Data and Control

Temporal logics are powerful tools that are widely used for the synthesis and verification of reactive systems. The recent progress on Large Language Models (LLMs) has the potential to make the process of writing such specifications more accessible. However, writing specifications in temporal logics remains challenging for all but the most expert users. A key question in using LLMs for temporal logic specification engineering is to understand what kind of guidance is most helpful to the LLM and the users to easily produce specifications. Looking specifically at the problem of reactive program synthesis, we explore the impact of providing an LLM with guidance on the separation of control and data--making explicit for the LLM what functionality is relevant for the specification, and treating the remaining functionality as an implementation detail for a series of pre-defined functions and predicates. We present a benchmark set and find that this separation of concerns improves specification generation. Our benchmark provides a test set against which to verify future work in LLM generation of temporal logic specifications.

cs.LG↗

arXiv2024

Statically Inferring Usage Bounds for Infrastructure as Code

Infrastructure as Code (IaC) has enabled cloud customers to have more agility in creating and modifying complex deployments of cloud-provisioned resources. By writing a configuration in IaC languages such as CloudFormation, users can declaratively specify their infrastructure and CloudFormation will handle the creation of the resources. However, understanding the complexity of IaC deployments has emerged as an unsolved issue. In particular, estimating the cost of an IaC deployment requires estimating the future usage and pricing models of every cloud resource in the deployment. Gaining transparency into predicted usage/costs is a leading challenge in cloud management. Existing work either relies on historical usage metrics to predict cost or on coarse-grain static analysis that ignores interactions between resources. Our key insight is that the topology of an IaC deployment imposes constraints on the usage of each resource, and we can formalize and automate the reasoning on constraints by using an SMT solver. This allows customers to have formal guarantees on the bounds of their cloud usage. We propose a tool for fine-grained static usage analysis that works by modeling the inter-resource interactions in an IaC deployment as a set of SMT constraints, and evaluate our tool on a benchmark of over 1000 real world IaC configurations.

cs.SE↗

arXiv2022

Succinct Explanations With Cascading Decision Trees

The decision tree is one of the most popular and classical machine learning models from the 1980s. However, in many practical applications, decision trees tend to generate decision paths with excessive depth. Long decision paths often cause overfitting problems, and make models difficult to interpret. With longer decision paths, inference is also more likely to fail when the data contain missing values. In this work, we propose a new tree model called Cascading Decision Trees to alleviate this problem. The key insight of Cascading Decision Trees is to separate the decision path and the explanation path. Our experiments show that on average, Cascading Decision Trees generate 63.38% shorter explanation paths, avoiding overfitting and thus achieve higher test accuracy. We also empirically demonstrate that Cascading Decision Trees have advantages in the robustness against missing values.

cs.LG↗

arXiv2021

Programming-By-Example by Programming-By-Example: Synthesis of Looping Programs

Program synthesis has seen many new applications in recent years, in large part thanks to the introduction of SyGuS. However, no existing SyGuS solvers have support for synthesizing recursive functions. We introduce an multi-phase algorithm for the synthesis of recursive ``looplike'' programs in SyGuS for programming-by-example. We solve constraints individually and treat them as ``unrolled`` examples of how a recursive program would behave, and solve for the generalized recursive solution. Our approach is modular and supports any SyGuS Solver.

cs.PL↗

arXiv2020

Grammar Filtering For Syntax-Guided Synthesis

Programming-by-example (PBE) is a synthesis paradigm that allows users to generate functions by simply providing input-output examples. While a promising interaction paradigm, synthesis is still too slow for realtime interaction and more widespread adoption. Existing approaches to PBE synthesis have used automated reasoning tools, such as SMT solvers, as well as works applying machine learning techniques. At its core, the automated reasoning approach relies on highly domain specific knowledge of programming languages. On the other hand, the machine learning approaches utilize the fact that when working with program code, it is possible to generate arbitrarily large training datasets. In this work, we propose a system for using machine learning in tandem with automated reasoning techniques to solve Syntax Guided Synthesis (SyGuS) style PBE problems. By preprocessing SyGuS PBE problems with a neural network, we can use a data driven approach to reduce the size of the search space, then allow automated reasoning-based solvers to more quickly find a solution analytically. Our system is able to run atop existing SyGuS PBE synthesis tools, decreasing the runtime of the winner of the 2019 SyGuS Competition for the PBE Strings track by 47.65% to outperform all of the competing tools.

cs.LG↗